{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LCIFRIIOUV32D3ESU22IMZ622O","short_pith_number":"pith:LCIFRIIO","schema_version":"1.0","canonical_sha256":"589058a10ea577a1ec92a6b48667dad3866dff84afcd4098b8758b7b16bdd17e","source":{"kind":"arxiv","id":"2009.14286","version":2},"attestation_state":"computed","paper":{"title":"Benign overfitting in ridge regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"A. Tsigler (1), P. L. Bartlett (1) ((1) UC Berkeley)","submitted_at":"2020-09-29T20:00:31Z","abstract_excerpt":"In many modern applications of deep learning the neural network has many more parameters than the data points used for its training. Motivated by those practices, a large body of recent theoretical research has been devoted to studying overparameterized models. One of the central phenomena in this regime is the ability of the model to interpolate noisy data, but still have test error lower than the amount of noise in that data. arXiv:1906.11300 characterized for which covariance structure of the data such a phenomenon can happen in linear regression if one considers the interpolating solution "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2009.14286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-09-29T20:00:31Z","cross_cats_sorted":["stat.ML","stat.TH"],"title_canon_sha256":"e965443facd876ef0a45f4090b2dfca54e45c4505f562c7531706638902c0530","abstract_canon_sha256":"ca0687a1a8c619d52ae8bb0909f1c6ab07e9013a0a9a4c3af58cae0ad0aa17a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:25.848027Z","signature_b64":"AnX7XrguhzRfumcmf3ivi1fLbT0YBXWbWbpuHvyOcUK/o8Cgch9jty5AOPLGTUiQhVo4PL01W6+gdmSY3mWmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"589058a10ea577a1ec92a6b48667dad3866dff84afcd4098b8758b7b16bdd17e","last_reissued_at":"2026-07-05T05:22:25.847594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:25.847594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benign overfitting in ridge regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"A. Tsigler (1), P. L. Bartlett (1) ((1) UC Berkeley)","submitted_at":"2020-09-29T20:00:31Z","abstract_excerpt":"In many modern applications of deep learning the neural network has many more parameters than the data points used for its training. Motivated by those practices, a large body of recent theoretical research has been devoted to studying overparameterized models. One of the central phenomena in this regime is the ability of the model to interpolate noisy data, but still have test error lower than the amount of noise in that data. arXiv:1906.11300 characterized for which covariance structure of the data such a phenomenon can happen in linear regression if one considers the interpolating solution "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.14286","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2009.14286/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2009.14286","created_at":"2026-07-05T05:22:25.847651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.14286v2","created_at":"2026-07-05T05:22:25.847651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.14286","created_at":"2026-07-05T05:22:25.847651+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCIFRIIOUV32","created_at":"2026-07-05T05:22:25.847651+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCIFRIIOUV32D3ES","created_at":"2026-07-05T05:22:25.847651+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCIFRIIO","created_at":"2026-07-05T05:22:25.847651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07694","citing_title":"Minimum Norm Interpolation via The Local Theory of Banach Spaces: The Role of Gaussianity","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10089","citing_title":"A Theory on Flow Matching with Neural Networks","ref_index":275,"is_internal_anchor":false},{"citing_arxiv_id":"2305.02304","citing_title":"New Equivalences Between Interpolation and SVMs: Kernels and Structured Features","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21494","citing_title":"Double descent for least-squares interpolation on contaminated data: A simulation study","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14473","citing_title":"Sharp convergence rates for Spectral methods via the feature space decomposition method","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2401.01335","citing_title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","ref_index":257,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCIFRIIOUV32D3ESU22IMZ622O","json":"https://pith.science/pith/LCIFRIIOUV32D3ESU22IMZ622O.json","graph_json":"https://pith.science/api/pith-number/LCIFRIIOUV32D3ESU22IMZ622O/graph.json","events_json":"https://pith.science/api/pith-number/LCIFRIIOUV32D3ESU22IMZ622O/events.json","paper":"https://pith.science/paper/LCIFRIIO"},"agent_actions":{"view_html":"https://pith.science/pith/LCIFRIIOUV32D3ESU22IMZ622O","download_json":"https://pith.science/pith/LCIFRIIOUV32D3ESU22IMZ622O.json","view_paper":"https://pith.science/paper/LCIFRIIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.14286&json=true","fetch_graph":"https://pith.science/api/pith-number/LCIFRIIOUV32D3ESU22IMZ622O/graph.json","fetch_events":"https://pith.science/api/pith-number/LCIFRIIOUV32D3ESU22IMZ622O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCIFRIIOUV32D3ESU22IMZ622O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCIFRIIOUV32D3ESU22IMZ622O/action/storage_attestation","attest_author":"https://pith.science/pith/LCIFRIIOUV32D3ESU22IMZ622O/action/author_attestation","sign_citation":"https://pith.science/pith/LCIFRIIOUV32D3ESU22IMZ622O/action/citation_signature","submit_replication":"https://pith.science/pith/LCIFRIIOUV32D3ESU22IMZ622O/action/replication_record"}},"created_at":"2026-07-05T05:22:25.847651+00:00","updated_at":"2026-07-05T05:22:25.847651+00:00"}